Paper: Weakly-Supervised Learning with Cost-Augmented Contrastive Estimation

ACL ID D14-1139
Title Weakly-Supervised Learning with Cost-Augmented Contrastive Estimation
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2014
Authors

We generalize contrastive estimation in two ways that permit adding more knowl- edge to unsupervised learning. The first allows the modeler to specify not only the set of corrupted inputs for each observa- tion, but also how bad each one is. The second allows specifying structural prefer- ences on the latent variable used to explain the observations. They require setting ad- ditional hyperparameters, which can be problematic in unsupervised learning, so we investigate new methods for unsuper- vised model selection and system com- bination. We instantiate these ideas for part-of-speech induction without tag dic- tionaries, improving over contrastive esti- mation as well as strong benchmarks from the PASCAL 2012 shared task.